Course content
This course is designed to equip students with foundational knowledge of machine learning and its application in business and society. Students will learn how to translate business questions into quantitative data-analytic tasks, study the principles and intuitions behind a variety of learning algorithms, and gain hands-on experience implementing machine learning models with Python. Importantly, students will also learn how to critically evaluate machine learning models for real-world relevance. This means not only being able to compare models with respect to predictive accuracy, but also to assess model fairness and perform appropriate mitigations, and to recognize when and why model outputs should not be interpreted in an explanatory way.
The course consists of weekly lectures, weekly exercise sessions, and a collaborative group project where students apply machine learning techniques to a topic and dataset of their own choosing.
Given the practical nature of this course, students with no prior programming experience are encouraged to complete a basic online tutorial to familiarize themselves with Python fundamentals (e.g., https://pandas.pydata.org/pandas-docs/version/0.15/10min.html). While the first two exercises provide a general introduction to programming with Python, the majority of the course is focused on implementing and evaluating machine learning models with libraries like 'pandas,' ‘scikit-learn,’ and ‘fairlearn.’
See course description in course catalogue